Multi-Level Feature-Based Ensemble Model for Target-Related Stance Detection

作     者：Shi Li Xinyan Cao Yiting Nan 

作者机构：School of Information EngineeringNortheast Forestry UniversityHarbinChina Petabase LLCWashington DC20001USA 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2020年第65卷第10期

页      面：777-788页

核心收录：

学科分类：0831[工学-生物医学工程（可授工学、理学、医学学位）] 0808[工学-电气工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 0805[工学-材料科学与工程（可授工学、理学学位）] 0701[理学-数学] 0801[工学-力学（可授工学、理学学位）] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work is supported by the Fundamental Research Funds for the Central Universities(Grant No.2572019BH03) 

主　　题：Attention sparse coding multi-level features ensemble model 

摘      要：Stance detection is the task of attitude identification toward a *** work of stance detection has focused on feature extraction but ignored the fact that irrelevant features exist as noise during higher-level ***,because the target is not always mentioned in the text,most methods have ignored target *** order to solve these problems,we propose a neural network ensemble method that combines the timing dependence bases on long short-term memory(LSTM)and the excellent extracting performance of convolutional neural networks(CNNs).The method can obtain multi-level features that consider both local and global *** also introduce attention mechanisms to magnify target information-related ***,we employ sparse coding to remove noise to obtain characteristic *** was improved by using sparse coding on the basis of attention employment and feature *** evaluate our approach on the SemEval-2016Task 6-A public dataset,achieving a performance that exceeds the benchmark and those of participating teams.